Related Experiment Video
Updated: Jun 20, 2026
Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
Published on: June 18, 2020
Identification of Neutrophil Extracellular Traps-Related Biomarkers in Multiple Myeloma Using Machine Learning and
Haoming Wu1, Yidong Zhu2, Bo Wang3
1Department of Traditional Chinese Medicine, Shanghai Fengxian District Hospital, Shanghai, 201400, China.
This study identified key Neutrophil Extracellular Traps (NETs)-related biomarkers, KIT, HGF, and F2RL1, for Multiple Myeloma (MM) using machine learning. Clinical validation confirmed their relevance, offering insights into MM
Area of Science:
- Hematological Malignancy Research
- Cancer Biomarker Discovery
- Immunology and Oncology
Background:
- Multiple Myeloma (MM) is a complex hematological malignancy driven by plasma cell proliferation.
- The role of Neutrophil Extracellular Traps (NETs) in MM pathogenesis is not well understood.
- Identifying NETs-related biomarkers is crucial for understanding MM and developing targeted therapies.
Purpose of the Study:
- To identify and validate NETs-related biomarkers for Multiple Myeloma (MM).
- To explore the underlying mechanisms and immune-related biological processes associated with these biomarkers.
- To predict potential therapeutic drugs targeting identified biomarkers in MM.
Main Methods:
- Analysis of three MM microarray datasets from the Gene Expression Omnibus (GEO) database.
- Application of differential expression and weighted gene co-expression network analyses to identify hub genes.
- Utilized machine learning algorithms for biomarker refinement and validation, including ROC analysis and nomogram construction.
- Experimental validation using quantitative real-time PCR on clinical MM samples.
Main Results:
- Identified 24 NETs-related hub genes, with KIT, HGF, and F2RL1 selected as core biomarkers.
- Developed a predictive model with good performance in training and external cohorts.
- Confirmed significant associations between biomarker genes and immune-related processes.
- Identified potential therapeutic drugs including Crizotinib and histamine.
- Validated biomarker gene expression patterns in clinical MM patient samples.
Conclusions:
- Successfully identified and validated key NETs-related biomarkers for MM using integrated machine learning and experimental approaches.
- These biomarkers hold potential for improving the understanding of the MM immune microenvironment.
- Findings provide a foundation for developing novel therapeutic strategies and clinical applications for MM treatment.
More Related Videos
08:59Neutrophil Extracellular Traps Generated by Low Density Neutrophils Obtained from Peritoneal Lavage Fluid Mediate Tumor Cell Growth and Attachment
Published on: August 3, 2018
07:18Quantifying Myeloperoxidase-DNA and Neutrophil Elastase-DNA Complexes from Neutrophil Extracellular Traps by Using a Modified Sandwich ELISA
Published on: May 12, 2023